Dataset Information

Imagined speech can be decoded from low- and cross-frequency intracranial EEG features.

ABSTRACT: Reconstructing intended speech from neural activity using brain-computer interfaces holds great promises for people with severe speech production deficits. While decoding overt speech has progressed, decoding imagined speech has met limited success, mainly because the associated neural signals are weak and variable compared to overt speech, hence difficult to decode by learning algorithms. We obtained three electrocorticography datasets from 13 patients, with electrodes implanted for epilepsy evaluation, who performed overt and imagined speech production tasks. Based on recent theories of speech neural processing, we extracted consistent and specific neural features usable for future brain computer interfaces, and assessed their performance to discriminate speech items in articulatory, phonetic, and vocalic representation spaces. While high-frequency activity provided the best signal for overt speech, both low- and higher-frequency power and local cross-frequency contributed to imagined speech decoding, in particular in phonetic and vocalic, i.e. perceptual, spaces. These findings show that low-frequency power and cross-frequency dynamics contain key information for imagined speech decoding.

SUBMITTER: Proix T

PROVIDER: S-EPMC8748882 | biostudies-literature | 2022 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Imagined speech can be decoded from low- and cross-frequency intracranial EEG features.

Proix Timothée T Delgado Saa Jaime J Christen Andy A Martin Stephanie S Pasley Brian N BN Knight Robert T RT Tian Xing X Poeppel David D Doyle Werner K WK Devinsky Orrin O Arnal Luc H LH Mégevand Pierre P Giraud Anne-Lise AL

Nature communications 20220110 1

Reconstructing intended speech from neural activity using brain-computer interfaces holds great promises for people with severe speech production deficits. While decoding overt speech has progressed, decoding imagined speech has met limited success, mainly because the associated neural signals are weak and variable compared to overt speech, hence difficult to decode by learning algorithms. We obtained three electrocorticography datasets from 13 patients, with electrodes implanted for epilepsy ev ...[more]

PMID: 35013268

Similar Datasets

Project description:ObjectiveHigh-frequency oscillations (HFOs) are a promising biomarker for the epileptogenic zone. However, no physiological definition of an HFO has been established, so detection relies on the empirical definition of an HFO derived from visual observation. This can bias estimates of HFO features such as amplitude and duration, thereby hindering their utility as biomarkers. Therefore, we set out to develop an algorithm that detects high-frequency events in the intracranial EEG that are morphologically distinct from background without requiring assumptions about event amplitude or shape.MethodWe propose the anomaly detection algorithm (ADA), which uses unsupervised machine learning to identify segments of data that are distinct from the background. We apply ADA and a standard HFO detector using a root mean square amplitude threshold to intracranial EEG from 11 patients undergoing evaluation for epilepsy surgery. The rate, amplitude, and duration of the detected events and the percent overlap between the two detectors are compared.ResultIn the seizure onset zone (SOZ), ADA detected a subset of conventional HFOs. In non-SOZ channels, ADA detected at least twice as many events as the standard approach, including some conventional HFOs; however, ADA also identified many low and intermediate amplitude events missed by the standard amplitude-based method. The rate of ADA events was similar across all channels; however, the amplitude of ADA events was significantly higher in SOZ channels (P < .0045), and the amplitude measurement was more stable over time than the HFO rate, as indicated by a lower coefficient of variation (P < .0125).SignificanceADA does not require human supervision, parameter optimization, or prior assumptions about event shape, amplitude, or duration. Our results suggest that the algorithm's estimate of event amplitude may differentiate SOZ and non-SOZ channels. Further studies will examine the utility of HFO amplitude as a biomarker for epilepsy surgical outcome.

Project description:BackgroundResting-state functional magnetic resonance imaging (rs-fMRI) is widely used to study brain functional alteration, but there have been no reports of research regarding the application of rs-fMRI in intracranial tuberculosis. The purpose of this prospective, cross-sectional study was to investigate spontaneous neural activity at different frequency bands in patients with intracranial tuberculosis using rs-fMRI with amplitude of low-frequency fluctuation (ALFF) and fractional ALFF (fALFF) methods.MethodsThe rs-fMRI data of 31 patients with intracranial tuberculosis and 30 gender-, age-, and education-matched healthy controls (HCs) were included. The ALFF and fALFF values in the conventional frequency band (0.01-0.08 Hz) and 2 sub-frequency bands (slow-4: 0.027-0.073 Hz; slow-5: 0.01-0.027 Hz) were calculated and compared between the groups. The resultant T-maps were corrected using the Gaussian random field (GRF) theory (voxel P<0.01, cluster P<0.05). Correlations between the ALFF and fALFF values and neurocognitive scores were assessed.ResultsCompared with the HCs, patients with intracranial tuberculosis showed decreased ALFF in the right paracentral lobule (T=-4.69) in the conventional frequency band, in the right supplementary motor area (T=-4.85) in the slow-4 band, and in the left supplementary motor area (T=-3.76) in the slow-5 band. Compared to the slow-5 band, the voxels with decreased ALFF were spatially more extensive in the slow-4 band. Compared with HCs, patients with intracranial tuberculosis showed decreased fALFF in the opercular parts of the right inferior frontal gyrus (T=-4.50) and the left inferior parietal lobe (T=-4.86) and increased fALFF in the left inferior cerebellum (T=5.84) in the conventional frequency band. In the slow-4 band, fALFF decreased in the opercular parts of the right inferior frontal gyrus (T=-5.29) and right precuneus (T=-4.34). In the slow-5 band, fALFF decreased in the left middle occipital gyrus (T=-4.65) and right middle frontal gyrus (T=-5.05).ConclusionsPatients with intracranial tuberculosis showed abnormal intrinsic brain activity at different frequency bands, and ALFF abnormalities in different brain regions could be better detected in the slow-4 band. This preliminary study might provide new insights into understanding the pathophysiological mechanism in intracranial tuberculosis.

Dataset Information

Imagined speech can be decoded from low- and cross-frequency intracranial EEG features.

Publications

Imagined speech can be decoded from low- and cross-frequency intracranial EEG features.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets